Use of neural networks for keyword generation
A system for identifying keywords in search results includes a plurality of neurons connected as a neural network, the neurons being associated with words and documents. An activity regulator regulates a minimum and/or maximum number of neurons of the neural network that are excited at any given time. Means for displaying the neurons to a user and identifying the neurons that correspond to keywords can be provided. Means for changing positions of the neurons relative to each other based on input from the user can be provided. The change in position of one neuron changes the keywords. The input from the user can be dragging a neuron on a display device, or changing a relevance of two neurons relative to each other. The neural network can be excited by a query that comprises words selected by a user. The neural network can be a bidirectional network. The user can inhibit neurons of the neural network by indicating irrelevance of a document. The neural network can be excited by a query that identifies a document considered relevant by a user. The neural network can also include neurons that represent groups of words. The neural network can be excited by a query that identifies a plurality of documents considered relevant by a user, and can output keywords associated with the plurality of documents.
1. A system for identifying keywords in search results comprising:
a processor;
a memory coupled to the processor;
computer code loaded into the memory for executing on the processor, for implementing the following functionality:
a plurality of neurons connected as a bidirectional neural network, the neurons being associated with words and documents, the neurons associated with words forming a first layer, and the neurons associated with documents forming a second layer,
each neuron having multiple inputs from other neurons, a single output connecting the neuron to other neurons, and a threshold function at the single output,
wherein at least some of the neurons of the first layer have connections between them and represent keywords in the documents;
an activity regulator that regulates a fraction of a number of neurons of the neural network that are excited at any given time; and
means for displaying to a user, on a display device, words of the search query and additional keywords from the documents and for identifying the neurons that correspond to keywords associated with at least one of the documents.
2. The system of claim 1 , further comprising means for changing positions of the keywords on a display relative to each other based on input from the user, wherein the change in position of one keyword changes the position of other displayed keywords.
3. The system of claim 2 , wherein the input from the user comprises dragging a keyword on a display device.
4. The system of claim 2 , wherein the input from the user comprises changing a relevance of neurons relative to each other.
5. The system of claim 1 , wherein the neural network is excited by a query that comprises words selected by a user.
6. The system of claim 1 , wherein the neural network is excited by a document selected by a user.
7. The system of claim 1 , wherein the keywords are generated based solely on a chosen document.
8. The system of claim 1 , wherein the keywords are generated based solely on a plurality of chosen documents.
9. The system of claim 1 , wherein the user can inhibit neurons of the neural network by indicating irrelevance of a document.
10. The system of claim 1 , wherein the user can inhibit neurons of the neural network by indicating irrelevance of a selected keyword.
11. The system of claim 1 , wherein the neural network is excited by a query that identifies a document considered relevant by a user.
12. The system of claim 1 , wherein the neural network also includes neurons having a group of words associated with a single neuron.
13. The system of claim 1 , wherein the neural network is excited by a query that identifies a plurality of documents considered relevant by a user, and wherein the neural network outputs keywords associated with the plurality of documents.
14. A system for identifying keywords, the system comprising:
a processor;
a memory coupled to the processor;
computer code loaded into the memory for executing on the processor, for implementing the following functionality:
a plurality of neurons arranged into a bidirectional neural network comprising a plurality of layers, the layers including words and documents,
the neurons associated with words forming a first layer, and the neurons associated with documents forming a second layer,
each neuron having multiple inputs from other neurons, a single output connecting the neuron to other neurons, and a threshold function at the single output,
wherein at least some of the neurons of the first layer have connections between them and represent keywords in the documents;
a plurality of connections between the neurons, wherein each neuron is connected to only some of the other neurons, such that at least some of the word neurons have connections between them;
wherein, in response to an input query, the neural network outputs a plurality of keywords associated with documents that are contextually relevant to the input query.
15. The system of claim 14 , wherein the input query identifies a plurality of documents considered relevant by a user, and wherein relevance of the identified documents is modified in response to user input.
16. The system of claim 14 , further comprising means for changing positions of the keywords relative to each on a display other based on input from the user, wherein the change in position of one keyword changes the keywords outputted by the neural network.
17. The system of claim 16 , wherein the input from the user comprises dragging a keyword on a display device.
18. The system of claim 16 , wherein the input from the user comprises changing a relevance of two neurons relative to each other.
19. The system of claim 14 , wherein the neural network is excited by a query that comprises words selected by a user.
20. The system of claim 14 , wherein the user can inhibit neurons of the neural network by indicating irrelevance of a document.
21. The system of claim 14 , wherein the neural network is excited by a query that identifies a document considered relevant by a user.
22. The system of claim 14 , wherein the neural network also includes neurons having a group of words associated with a single neuron.
23. The system of claim 14 , wherein the neural network is excited by a document selected by a user.
24. A computer implemented method for identifying keywords, the method computer-executable code stored on a computer-readable medium, for performing the steps of:
arranging a plurality of neurons arranged a bidirectional neural network comprising a plurality of layers, the layers including words and documents,
each neuron having multiple inputs from other neurons, a single output connecting the neuron to other neurons, and a threshold function at the single output,
forming a first layer of the neural network from the neurons associated with words;
forming a second layer of the neural network from the neurons associated with documents;
forming a plurality of connections between the neurons, wherein each neuron is connected to only some of the other neurons, such that at least some of the word neurons have connections between them,
wherein at least some of the neurons of the first layer have connections between them and represent keywords in the documents, and
in response to an input query, outputting, to a user, a plurality of keywords associated with documents that are contextually relevant to the input query.